Human Frontier
85.5
Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.
Blended Price
$1.13/M
Input Price
$0.50/M
Output Price
$3.00/M
Speed
—
TTFT
—
Axes
Filters
Providers
vcontinuous-leaderboard · tasks-created:2025-12-01:2026-03-01 · Gemini 3 Flash Preview · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Gemini 3 Flash Preview__tools · record Gemini 3 Flash Preview__tools:1764547200000:1772323200000
{
"passAt5": 65.359477124183,
"developer": "google",
"instanceType": "model",
"contextPolicy": "128k unless the model supports less",
"attemptsPerTask": 5,
"totalTokenUsage": 2011252.2615411077,
"modelReleaseDate": "2025-12-17",
"scoreStandardError": 0.4168980195749748,
"cachedTokenPercentage": 75.9805341681911,
"modelReleaseTimestamp": 1765929600000,
"standardContextTokens": 128000,
"averageInstanceCostUsd": 0.2892457823095115,
"potentialContamination": true,
"aggregateTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1764547200000
},
"publishedTaskRangeTimestamp": {
"to": 1772323200000,
"from": 1764547200000
}
}Evidence observed 2026-03-01